From 39e63bd2d848667e44fc05d8a39460f29a3dfbe1 Mon Sep 17 00:00:00 2001
From: Craig Topper <craig.topper@sifive.com>
Date: Mon, 9 May 2022 21:37:23 -0700
Subject: [PATCH] [IR][CostModel] A scalable vector shuffle can't be an
 identity or reverse shuffle.

Even if the minimum number of elements is 1 and the length doesn't change,
we don't know what vscale is so we can't classify it as identity mask. Instead it
is a zero element splat.

For reverse, we shouldn't classify it as a reverse unless there are at least 2 elements
in the mask. This applies to both fixed and scalable vectors. For fixed vectors, a single
element would be an identity shuffle. For scalable vector it's a zero elt splat.

Reviewed By: sdesmalen, liaolucy

Differential Revision: https://reviews.llvm.org/D124655
---
 llvm/include/llvm/IR/Instructions.h                     | 11 +++++++++++
 llvm/lib/IR/Instructions.cpp                            |  8 +++++++-
 llvm/test/Analysis/CostModel/RISCV/rvv-shuffle.ll       |  2 +-
 llvm/test/Analysis/CostModel/RISCV/shuffle-broadcast.ll | 16 ++++++++--------
 4 files changed, 27 insertions(+), 10 deletions(-)

diff --git a/llvm/include/llvm/IR/Instructions.h b/llvm/include/llvm/IR/Instructions.h
index c9d4808..fd922c4 100644
--- a/llvm/include/llvm/IR/Instructions.h
+++ b/llvm/include/llvm/IR/Instructions.h
@@ -2137,6 +2137,12 @@ public:
   static bool isIdentityMask(ArrayRef<int> Mask);
   static bool isIdentityMask(const Constant *Mask) {
     assert(Mask->getType()->isVectorTy() && "Shuffle needs vector constant.");
+
+    // Not possible to express a shuffle mask for a scalable vector for this
+    // case.
+    if (isa<ScalableVectorType>(Mask->getType()))
+      return false;
+
     SmallVector<int, 16> MaskAsInts;
     getShuffleMask(Mask, MaskAsInts);
     return isIdentityMask(MaskAsInts);
@@ -2147,6 +2153,11 @@ public:
   /// from its input vectors.
   /// Example: shufflevector <4 x n> A, <4 x n> B, <4,undef,6,undef>
   bool isIdentity() const {
+    // Not possible to express a shuffle mask for a scalable vector for this
+    // case.
+    if (isa<ScalableVectorType>(getType()))
+      return false;
+
     return !changesLength() && isIdentityMask(ShuffleMask);
   }
 
diff --git a/llvm/lib/IR/Instructions.cpp b/llvm/lib/IR/Instructions.cpp
index 4eb1e817..7615a4d 100644
--- a/llvm/lib/IR/Instructions.cpp
+++ b/llvm/lib/IR/Instructions.cpp
@@ -2216,7 +2216,13 @@ bool ShuffleVectorInst::isIdentityMask(ArrayRef<int> Mask) {
 bool ShuffleVectorInst::isReverseMask(ArrayRef<int> Mask) {
   if (!isSingleSourceMask(Mask))
     return false;
-  for (int i = 0, NumElts = Mask.size(); i < NumElts; ++i) {
+
+  // The number of elements in the mask must be at least 2.
+  int NumElts = Mask.size();
+  if (NumElts < 2)
+    return false;
+
+  for (int i = 0; i < NumElts; ++i) {
     if (Mask[i] == -1)
       continue;
     if (Mask[i] != (NumElts - 1 - i) && Mask[i] != (NumElts + NumElts - 1 - i))
diff --git a/llvm/test/Analysis/CostModel/RISCV/rvv-shuffle.ll b/llvm/test/Analysis/CostModel/RISCV/rvv-shuffle.ll
index 1650ae3..b83ebf8 100644
--- a/llvm/test/Analysis/CostModel/RISCV/rvv-shuffle.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/rvv-shuffle.ll
@@ -11,7 +11,7 @@ define void  @vector_broadcast() {
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %3 = shufflevector <vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i32> zeroinitializer
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %4 = shufflevector <vscale x 2 x i32> undef, <vscale x 2 x i32> undef, <vscale x 2 x i32> zeroinitializer
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %5 = shufflevector <vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i32> zeroinitializer
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %6 = shufflevector <vscale x 1 x i64> undef, <vscale x 1 x i64> undef, <vscale x 1 x i32> zeroinitializer
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = shufflevector <vscale x 1 x i64> undef, <vscale x 1 x i64> undef, <vscale x 1 x i32> zeroinitializer
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = shufflevector <vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i32> zeroinitializer
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %8 = shufflevector <vscale x 16 x i1> undef, <vscale x 16 x i1> undef, <vscale x 16 x i32> zeroinitializer
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %9 = shufflevector <vscale x 8 x i1> undef, <vscale x 8 x i1> undef, <vscale x 8 x i32> zeroinitializer
diff --git a/llvm/test/Analysis/CostModel/RISCV/shuffle-broadcast.ll b/llvm/test/Analysis/CostModel/RISCV/shuffle-broadcast.ll
index 6f01149..0cb57e1 100644
--- a/llvm/test/Analysis/CostModel/RISCV/shuffle-broadcast.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/shuffle-broadcast.ll
@@ -3,44 +3,44 @@
 
 define void  @broadcast() #0{
 ; CHECK-LABEL: 'broadcast'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %zero = shufflevector <vscale x 1 x half> undef, <vscale x 1 x half> undef, <vscale x 1 x i32> zeroinitializer
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %zero = shufflevector <vscale x 1 x half> undef, <vscale x 1 x half> undef, <vscale x 1 x i32> zeroinitializer
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %1 = shufflevector <vscale x 2 x half> undef, <vscale x 2 x half> undef, <vscale x 2 x i32> zeroinitializer
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %2 = shufflevector <vscale x 4 x half> undef, <vscale x 4 x half> undef, <vscale x 4 x i32> zeroinitializer
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %3 = shufflevector <vscale x 8 x half> undef, <vscale x 8 x half> undef, <vscale x 8 x i32> zeroinitializer
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %4 = shufflevector <vscale x 16 x half> undef, <vscale x 16 x half> undef, <vscale x 16 x i32> zeroinitializer
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %5 = shufflevector <vscale x 32 x half> undef, <vscale x 32 x half> undef, <vscale x 32 x i32> zeroinitializer
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %6 = shufflevector <vscale x 1 x float> undef, <vscale x 1 x float> undef, <vscale x 1 x i32> zeroinitializer
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = shufflevector <vscale x 1 x float> undef, <vscale x 1 x float> undef, <vscale x 1 x i32> zeroinitializer
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = shufflevector <vscale x 2 x float> undef, <vscale x 2 x float> undef, <vscale x 2 x i32> zeroinitializer
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %8 = shufflevector <vscale x 4 x float> undef, <vscale x 4 x float> undef, <vscale x 4 x i32> zeroinitializer
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %9 = shufflevector <vscale x 8 x float> undef, <vscale x 8 x float> undef, <vscale x 8 x i32> zeroinitializer
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %10 = shufflevector <vscale x 16 x float> undef, <vscale x 16 x float> undef, <vscale x 16 x i32> zeroinitializer
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %11 = shufflevector <vscale x 1 x double> undef, <vscale x 1 x double> undef, <vscale x 1 x i32> zeroinitializer
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %11 = shufflevector <vscale x 1 x double> undef, <vscale x 1 x double> undef, <vscale x 1 x i32> zeroinitializer
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %12 = shufflevector <vscale x 2 x double> undef, <vscale x 2 x double> undef, <vscale x 2 x i32> zeroinitializer
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %13 = shufflevector <vscale x 4 x double> undef, <vscale x 4 x double> undef, <vscale x 4 x i32> zeroinitializer
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %14 = shufflevector <vscale x 8 x double> undef, <vscale x 8 x double> undef, <vscale x 8 x i32> zeroinitializer
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %15 = shufflevector <vscale x 1 x i8> undef, <vscale x 1 x i8> undef, <vscale x 1 x i32> zeroinitializer
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %15 = shufflevector <vscale x 1 x i8> undef, <vscale x 1 x i8> undef, <vscale x 1 x i32> zeroinitializer
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %16 = shufflevector <vscale x 2 x i8> undef, <vscale x 2 x i8> undef, <vscale x 2 x i32> zeroinitializer
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %17 = shufflevector <vscale x 4 x i8> undef, <vscale x 4 x i8> undef, <vscale x 4 x i32> zeroinitializer
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %18 = shufflevector <vscale x 8 x i8> undef, <vscale x 8 x i8> undef, <vscale x 8 x i32> zeroinitializer
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %19 = shufflevector <vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i32> zeroinitializer
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %20 = shufflevector <vscale x 32 x i8> undef, <vscale x 32 x i8> undef, <vscale x 32 x i32> zeroinitializer
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %21 = shufflevector <vscale x 64 x i8> undef, <vscale x 64 x i8> undef, <vscale x 64 x i32> zeroinitializer
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %22 = shufflevector <vscale x 1 x i16> undef, <vscale x 1 x i16> undef, <vscale x 1 x i32> zeroinitializer
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %22 = shufflevector <vscale x 1 x i16> undef, <vscale x 1 x i16> undef, <vscale x 1 x i32> zeroinitializer
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %23 = shufflevector <vscale x 2 x i16> undef, <vscale x 2 x i16> undef, <vscale x 2 x i32> zeroinitializer
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %24 = shufflevector <vscale x 4 x i16> undef, <vscale x 4 x i16> undef, <vscale x 4 x i32> zeroinitializer
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %25 = shufflevector <vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i32> zeroinitializer
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %26 = shufflevector <vscale x 16 x i16> undef, <vscale x 16 x i16> undef, <vscale x 16 x i32> zeroinitializer
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %27 = shufflevector <vscale x 32 x i16> undef, <vscale x 32 x i16> undef, <vscale x 32 x i32> zeroinitializer
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %28 = shufflevector <vscale x 1 x i32> undef, <vscale x 1 x i32> undef, <vscale x 1 x i32> zeroinitializer
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %28 = shufflevector <vscale x 1 x i32> undef, <vscale x 1 x i32> undef, <vscale x 1 x i32> zeroinitializer
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %29 = shufflevector <vscale x 2 x i32> undef, <vscale x 2 x i32> undef, <vscale x 2 x i32> zeroinitializer
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %30 = shufflevector <vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i32> zeroinitializer
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %31 = shufflevector <vscale x 8 x i32> undef, <vscale x 8 x i32> undef, <vscale x 8 x i32> zeroinitializer
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %32 = shufflevector <vscale x 16 x i32> undef, <vscale x 16 x i32> undef, <vscale x 16 x i32> zeroinitializer
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %33 = shufflevector <vscale x 1 x i64> undef, <vscale x 1 x i64> undef, <vscale x 1 x i32> zeroinitializer
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %33 = shufflevector <vscale x 1 x i64> undef, <vscale x 1 x i64> undef, <vscale x 1 x i32> zeroinitializer
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %34 = shufflevector <vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i32> zeroinitializer
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %35 = shufflevector <vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i32> zeroinitializer
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %36 = shufflevector <vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i32> zeroinitializer
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %37 = shufflevector <vscale x 1 x i1> undef, <vscale x 1 x i1> undef, <vscale x 1 x i32> zeroinitializer
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %37 = shufflevector <vscale x 1 x i1> undef, <vscale x 1 x i1> undef, <vscale x 1 x i32> zeroinitializer
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %38 = shufflevector <vscale x 2 x i1> undef, <vscale x 2 x i1> undef, <vscale x 2 x i32> zeroinitializer
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %39 = shufflevector <vscale x 4 x i1> undef, <vscale x 4 x i1> undef, <vscale x 4 x i32> zeroinitializer
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %40 = shufflevector <vscale x 8 x i1> undef, <vscale x 8 x i1> undef, <vscale x 8 x i32> zeroinitializer
-- 
2.7.4